© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 233439
    Prev
    Next
    INDEX
    Explanations

    governs, supports, brands, use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >
    0.54
    naya
    0.49
    Ain
    0.48
    >().
    0.47
     impair
    0.46
    Chronic
    0.45
     kanker
    0.45
     assez
    0.45
     ⋅
    0.45
    ieuses
    0.44
    POSITIVE LOGITS
     வரை
    0.50
    ர
    0.50
    ली
    0.50
    эр
    0.49
    ivar
    0.49
     Türkiye
    0.46
    на
    0.45
     Jenny
    0.45
    buttonLevel
    0.45
    னி
    0.45
    Activations Density 0.001%

    No Known Activations